Commit f39b4d8ba4659f5ffd97ef9d87ce3d7108231450
1 parent
57ff8482ac
Exists in
main
Finished the preprocessing.
Showing 1 changed file with 34 additions and 54 deletions Inline Diff
python-notebook/data_loading.ipynb
View file @
f39b4d8
| { | 1 | 1 | { | |
| "cells": [ | 2 | 2 | "cells": [ | |
| { | 3 | 3 | { | |
| "cell_type": "markdown", | 4 | 4 | "cell_type": "markdown", | |
| "metadata": {}, | 5 | 5 | "metadata": {}, | |
| "source": [ | 6 | 6 | "source": [ | |
| "# Loading libraries" | 7 | 7 | "# Loading libraries" | |
| ] | 8 | 8 | ] | |
| }, | 9 | 9 | }, | |
| { | 10 | 10 | { | |
| "cell_type": "code", | 11 | 11 | "cell_type": "code", | |
| "execution_count": 17, | 12 | 12 | "execution_count": 17, | |
| "metadata": {}, | 13 | 13 | "metadata": {}, | |
| "outputs": [], | 14 | 14 | "outputs": [], | |
| "source": [ | 15 | 15 | "source": [ | |
| "import numpy as np\n", | 16 | 16 | "import numpy as np\n", | |
| "import matplotlib.pyplot as plt\n", | 17 | 17 | "import matplotlib.pyplot as plt\n", | |
| "import seaborn as sns\n", | 18 | 18 | "import seaborn as sns\n", | |
| "from pandas import read_csv\n", | 19 | 19 | "from pandas import read_csv\n", | |
| "import pandas as pd\n", | 20 | 20 | "import pandas as pd\n", | |
| "import os\n", | 21 | 21 | "import os\n", | |
| "from datetime import datetime, date, timedelta\n", | 22 | 22 | "from datetime import datetime, date, timedelta\n", | |
| "from itertools import product\n", | 23 | 23 | "from itertools import product\n", | |
| "# %load_ext line_profiler" | 24 | 24 | "# %load_ext line_profiler" | |
| ] | 25 | 25 | ] | |
| }, | 26 | 26 | }, | |
| { | 27 | 27 | { | |
| "cell_type": "markdown", | 28 | 28 | "cell_type": "markdown", | |
| "metadata": {}, | 29 | 29 | "metadata": {}, | |
| "source": [ | 30 | 30 | "source": [ | |
| "# Defining Functions and Adjusting Settings" | 31 | 31 | "# Defining Functions and Adjusting Settings" | |
| ] | 32 | 32 | ] | |
| }, | 33 | 33 | }, | |
| { | 34 | 34 | { | |
| "cell_type": "code", | 35 | 35 | "cell_type": "code", | |
| "execution_count": 36, | 36 | 36 | "execution_count": 36, | |
| "metadata": {}, | 37 | 37 | "metadata": {}, | |
| "outputs": [], | 38 | 38 | "outputs": [], | |
| "source": [ | 39 | 39 | "source": [ | |
| "pd.options.mode.chained_assignment = None\n", | 40 | 40 | "pd.options.mode.chained_assignment = None\n", | |
| "\n", | 41 | 41 | "\n", | |
| "def get_date(x):\n", | 42 | 42 | "def get_date(x):\n", | |
| " return date(x.year, x.month, x.day)\n", | 43 | 43 | " return date(x.year, x.month, x.day)\n", | |
| "\n", | 44 | 44 | "\n", | |
| "def get_minute_index(x):\n", | 45 | 45 | "def get_minute_index(x):\n", | |
| " return (x.hour * 60) + x.minute\n", | 46 | 46 | " return (x.hour * 60) + x.minute\n", | |
| "\n", | 47 | 47 | "\n", | |
| "\n", | 48 | 48 | "\n", | |
| "# cut off values that are not in the range of the data\n", | 49 | 49 | "# cut off values that are not in the range of the data\n", | |
| "THRESHOLD_OF_DAYS_PER_USER = 10\n", | 50 | 50 | "THRESHOLD_OF_DAYS_PER_USER = 10\n", | |
| "\n", | 51 | 51 | "\n", | |
| "# cut off values for the number of consecutive minutes for a walk\n", | 52 | 52 | "# cut off values for the number of consecutive minutes for a walk\n", | |
| "MINIMUM_NUMBER_OF_MINUTES_FOR_A_WALK = 5\n", | 53 | 53 | "MINIMUM_NUMBER_OF_MINUTES_FOR_A_WALK = 5\n", | |
| "\n", | 54 | 54 | "\n", | |
| "# cut off values for the number of steps per minute for an active minute\n", | 55 | 55 | "# cut off values for the number of steps per minute for an active minute\n", | |
| "MINIMUM_STEPS_PER_MINUTE = 60\n" | 56 | 56 | "MINIMUM_STEPS_PER_MINUTE = 60\n" | |
| ] | 57 | 57 | ] | |
| }, | 58 | 58 | }, | |
| { | 59 | 59 | { | |
| "cell_type": "markdown", | 60 | 60 | "cell_type": "markdown", | |
| "metadata": {}, | 61 | 61 | "metadata": {}, | |
| "source": [ | 62 | 62 | "source": [ | |
| "# Loading data files" | 63 | 63 | "# Loading data files" | |
| ] | 64 | 64 | ] | |
| }, | 65 | 65 | }, | |
| { | 66 | 66 | { | |
| "cell_type": "code", | 67 | 67 | "cell_type": "code", | |
| "execution_count": 5, | 68 | 68 | "execution_count": 5, | |
| "metadata": {}, | 69 | 69 | "metadata": {}, | |
| "outputs": [], | 70 | 70 | "outputs": [], | |
| "source": [ | 71 | 71 | "source": [ | |
| "data_dir = '../data'\n", | 72 | 72 | "data_dir = '../data'\n", | |
| "\n", | 73 | 73 | "\n", | |
| "daily = read_csv(os.path.join(data_dir, 'daily.csv'))\n", | 74 | 74 | "daily = read_csv(os.path.join(data_dir, 'daily.csv'))\n", | |
| "dose = read_csv(os.path.join(data_dir, 'dose.csv'))\n", | 75 | 75 | "dose = read_csv(os.path.join(data_dir, 'dose.csv'))\n", | |
| "jawbone = read_csv(os.path.join(data_dir, 'jawbone.csv'), low_memory=False)\n" | 76 | 76 | "jawbone = read_csv(os.path.join(data_dir, 'jawbone.csv'), low_memory=False)\n" | |
| ] | 77 | 77 | ] | |
| }, | 78 | 78 | }, | |
| { | 79 | 79 | { | |
| "cell_type": "markdown", | 80 | 80 | "cell_type": "markdown", | |
| "metadata": {}, | 81 | 81 | "metadata": {}, | |
| "source": [ | 82 | 82 | "source": [ | |
| "# Preprocessing\n", | 83 | 83 | "# Preprocessing\n", | |
| "## Picking up the variables" | 84 | 84 | "## Picking up the variables" | |
| ] | 85 | 85 | ] | |
| }, | 86 | 86 | }, | |
| { | 87 | 87 | { | |
| "cell_type": "code", | 88 | 88 | "cell_type": "code", | |
| "execution_count": 6, | 89 | 89 | "execution_count": 6, | |
| "metadata": {}, | 90 | 90 | "metadata": {}, | |
| "outputs": [], | 91 | 91 | "outputs": [], | |
| "source": [ | 92 | 92 | "source": [ | |
| "# Column names of jawbone data\n", | 93 | 93 | "# Column names of jawbone data\n", | |
| "# 'Var1', 'user', 'start_datetime', 'end_datetime', 'timezone', 'userid',\n", | 94 | 94 | "# 'Var1', 'user', 'start_datetime', 'end_datetime', 'timezone', 'userid',\n", | |
| "# 'steps', 'gmtoff', 'tz', 'start_date', 'end_date', 'start_utime',\n", | 95 | 95 | "# 'steps', 'gmtoff', 'tz', 'start_date', 'end_date', 'start_utime',\n", | |
| "# 'end_utime', 'start_udate', 'end_udate', 'intake_date', 'intake_utime',\n", | 96 | 96 | "# 'end_utime', 'start_udate', 'end_udate', 'intake_date', 'intake_utime',\n", | |
| "# 'intake_tz', 'intake_gmtoff', 'intake_hour', 'intake_min',\n", | 97 | 97 | "# 'intake_tz', 'intake_gmtoff', 'intake_hour', 'intake_min',\n", | |
| "# 'intake_slot', 'travel_start', 'travel_end', 'exit_date',\n", | 98 | 98 | "# 'intake_slot', 'travel_start', 'travel_end', 'exit_date',\n", | |
| "# 'dropout_date', 'last_date', 'last_utime', 'last_tz', 'last_gmtoff',\n", | 99 | 99 | "# 'dropout_date', 'last_date', 'last_utime', 'last_tz', 'last_gmtoff',\n", | |
| "# 'last_hour', 'last_min', 'start_utime_local', 'end_utime_local'\n", | 100 | 100 | "# 'last_hour', 'last_min', 'start_utime_local', 'end_utime_local'\n", | |
| "\n", | 101 | 101 | "\n", | |
| "\n", | 102 | 102 | "\n", | |
| "# duplicate jawbone data\n", | 103 | 103 | "# duplicate jawbone data\n", | |
| "jawbone2 = jawbone.copy(deep=True)\n", | 104 | 104 | "jawbone2 = jawbone.copy(deep=True)\n", | |
| "\n", | 105 | 105 | "\n", | |
| "# convert string datetimes to actual datetime objects\n", | 106 | 106 | "# convert string datetimes to actual datetime objects\n", | |
| "jawbone2[\"start_utime_local\"] = pd.to_datetime(\n", | 107 | 107 | "jawbone2[\"start_utime_local\"] = pd.to_datetime(\n", | |
| " jawbone2[\"start_utime_local\"], format=\"%Y-%m-%d %H:%M:%S\")\n", | 108 | 108 | " jawbone2[\"start_utime_local\"], format=\"%Y-%m-%d %H:%M:%S\")\n", | |
| "jawbone2[\"start_datetime\"] = pd.to_datetime(\n", | 109 | 109 | "jawbone2[\"start_datetime\"] = pd.to_datetime(\n", | |
| " jawbone2[\"start_datetime\"], format=\"%Y-%m-%d %H:%M:%S\")\n", | 110 | 110 | " jawbone2[\"start_datetime\"], format=\"%Y-%m-%d %H:%M:%S\")\n", | |
| "\n", | 111 | 111 | "\n", | |
| "# calculate the timezone offset\n", | 112 | 112 | "# calculate the timezone offset\n", | |
| "jawbone2[\"tz_offset\"] = jawbone2[\"start_datetime\"] - \\\n", | 113 | 113 | "jawbone2[\"tz_offset\"] = jawbone2[\"start_datetime\"] - \\\n", | |
| " jawbone2[\"start_utime_local\"]\n", | 114 | 114 | " jawbone2[\"start_utime_local\"]\n", | |
| "\n", | 115 | 115 | "\n", | |
| "\n", | 116 | 116 | "\n", | |
| "# selecting only important columns\n", | 117 | 117 | "# selecting only important columns\n", | |
| "jawbone3 = jawbone2[[\"user\", \"start_utime_local\",\n", | 118 | 118 | "jawbone3 = jawbone2[[\"user\", \"start_utime_local\",\n", | |
| " \"end_utime_local\", \"tz_offset\", \"steps\"]]\n", | 119 | 119 | " \"end_utime_local\", \"tz_offset\", \"steps\"]]\n", | |
| "\n", | 120 | 120 | "\n", | |
| "# picking up the local date\n", | 121 | 121 | "# picking up the local date\n", | |
| "jawbone3[\"local_date\"] = jawbone3[\"start_utime_local\"].apply(get_date)\n", | 122 | 122 | "jawbone3[\"local_date\"] = jawbone3[\"start_utime_local\"].apply(get_date)\n", | |
| "\n", | 123 | 123 | "\n", | |
| "# picking up the local minute index\n", | 124 | 124 | "# picking up the local minute index\n", | |
| "jawbone3[\"local_minute_index\"] = jawbone3[\"start_utime_local\"].apply(\n", | 125 | 125 | "jawbone3[\"local_minute_index\"] = jawbone3[\"start_utime_local\"].apply(\n", | |
| " get_minute_index)\n" | 126 | 126 | " get_minute_index)\n" | |
| ] | 127 | 127 | ] | |
| }, | 128 | 128 | }, | |
| { | 129 | 129 | { | |
| "cell_type": "markdown", | 130 | 130 | "cell_type": "markdown", | |
| "metadata": {}, | 131 | 131 | "metadata": {}, | |
| "source": [ | 132 | 132 | "source": [ | |
| "## Making a key info database" | 133 | 133 | "## Making a key info database" | |
| ] | 134 | 134 | ] | |
| }, | 135 | 135 | }, | |
| { | 136 | 136 | { | |
| "cell_type": "code", | 137 | 137 | "cell_type": "code", | |
| "execution_count": 7, | 138 | 138 | "execution_count": 7, | |
| "metadata": {}, | 139 | 139 | "metadata": {}, | |
| "outputs": [], | 140 | 140 | "outputs": [], | |
| "source": [ | 141 | 141 | "source": [ | |
| "# picking up the user - date data\n", | 142 | 142 | "# picking up the user - date data\n", | |
| "user_date = jawbone3[[\"user\", \"local_date\"]].drop_duplicates()" | 143 | 143 | "user_date = jawbone3[[\"user\", \"local_date\"]].drop_duplicates()" | |
| ] | 144 | 144 | ] | |
| }, | 145 | 145 | }, | |
| { | 146 | 146 | { | |
| "cell_type": "markdown", | 147 | 147 | "cell_type": "markdown", | |
| "metadata": {}, | 148 | 148 | "metadata": {}, | |
| "source": [ | 149 | 149 | "source": [ | |
| "## Removing users with too small amount of data" | 150 | 150 | "## Removing users with too small amount of data" | |
| ] | 151 | 151 | ] | |
| }, | 152 | 152 | }, | |
| { | 153 | 153 | { | |
| "cell_type": "code", | 154 | 154 | "cell_type": "code", | |
| "execution_count": 13, | 155 | 155 | "execution_count": 13, | |
| "metadata": {}, | 156 | 156 | "metadata": {}, | |
| "outputs": [ | 157 | 157 | "outputs": [ | |
| { | 158 | 158 | { | |
| "name": "stdout", | 159 | 159 | "name": "stdout", | |
| "output_type": "stream", | 160 | 160 | "output_type": "stream", | |
| "text": [ | 161 | 161 | "text": [ | |
| "Threshold: 10\n", | 162 | 162 | "Threshold: 10\n", | |
| "Users to be removed:[12, 36, 38]\n", | 163 | 163 | "Users to be removed:[12, 36, 38]\n", | |
| "Shape Change: 258889 -> 258363 (-526, -0.2%)\n" | 164 | 164 | "Shape Change: 258889 -> 258363 (-526, -0.2%)\n" | |
| ] | 165 | 165 | ] | |
| }, | 166 | 166 | }, | |
| { | 167 | 167 | { | |
| "data": { | 168 | 168 | "data": { | |
| "image/png": "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", | 169 | 169 | "image/png": "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", | |
| "text/plain": [ | 170 | 170 | "text/plain": [ | |
| "<Figure size 432x288 with 1 Axes>" | 171 | 171 | "<Figure size 432x288 with 1 Axes>" | |
| ] | 172 | 172 | ] | |
| }, | 173 | 173 | }, | |
| "metadata": {}, | 174 | 174 | "metadata": {}, | |
| "output_type": "display_data" | 175 | 175 | "output_type": "display_data" | |
| } | 176 | 176 | } | |
| ], | 177 | 177 | ], | |
| "source": [ | 178 | 178 | "source": [ | |
| "# making a stat of the number of days per user\n", | 179 | 179 | "# making a stat of the number of days per user\n", | |
| "stat_user = user_date.groupby(['user'])['local_date'].nunique().sort_values()\n", | 180 | 180 | "stat_user = user_date.groupby(['user'])['local_date'].nunique().sort_values()\n", | |
| "\n", | 181 | 181 | "\n", | |
| "ax = plt.figure()\n", | 182 | 182 | "ax = plt.figure()\n", | |
| "ax.patch.set_facecolor('white')\n", | 183 | 183 | "ax.patch.set_facecolor('white')\n", | |
| "ax = sns.histplot(stat_user)\n", | 184 | 184 | "ax = sns.histplot(stat_user)\n", | |
| "ax.set_title('Distribution of number of days per user')\n", | 185 | 185 | "ax.set_title('Distribution of number of days per user')\n", | |
| "ax.set_xlabel('Number of days')\n", | 186 | 186 | "ax.set_xlabel('Number of days')\n", | |
| "ax.set_ylabel('Frequency')\n", | 187 | 187 | "ax.set_ylabel('Frequency')\n", | |
| "\n", | 188 | 188 | "\n", | |
| "\n", | 189 | 189 | "\n", | |
| "# filter out users that have less days of data than THRESHOLD_OF_DAYS_PER_USER\n", | 190 | 190 | "# filter out users that have less days of data than THRESHOLD_OF_DAYS_PER_USER\n", | |
| "users_to_be_removed = stat_user[stat_user < THRESHOLD_OF_DAYS_PER_USER].index\n", | 191 | 191 | "users_to_be_removed = stat_user[stat_user < THRESHOLD_OF_DAYS_PER_USER].index\n", | |
| "\n", | 192 | 192 | "\n", | |
| "print(\"Threshold: {}\".format(THRESHOLD_OF_DAYS_PER_USER))\n", | 193 | 193 | "print(\"Threshold: {}\".format(THRESHOLD_OF_DAYS_PER_USER))\n", | |
| "print(\"Users to be removed:{}\".format(list(users_to_be_removed)))\n", | 194 | 194 | "print(\"Users to be removed:{}\".format(list(users_to_be_removed)))\n", | |
| "\n", | 195 | 195 | "\n", | |
| "jawbone4 = jawbone3[~jawbone3[\"user\"].isin(users_to_be_removed)]\n", | 196 | 196 | "jawbone4 = jawbone3[~jawbone3[\"user\"].isin(users_to_be_removed)]\n", | |
| "\n", | 197 | 197 | "\n", | |
| "user_date2 = user_date[~user_date[\"user\"].isin(users_to_be_removed)]\n", | 198 | 198 | "user_date2 = user_date[~user_date[\"user\"].isin(users_to_be_removed)]\n", | |
| "\n", | 199 | 199 | "\n", | |
| "# printing the amount of data removed\n", | 200 | 200 | "# printing the amount of data removed\n", | |
| "jawbone3_count, _ = jawbone3.shape\n", | 201 | 201 | "jawbone3_count, _ = jawbone3.shape\n", | |
| "jawbone4_count, _ = jawbone4.shape\n", | 202 | 202 | "jawbone4_count, _ = jawbone4.shape\n", | |
| "\n", | 203 | 203 | "\n", | |
| "print(\"Shape Change: {} -> {} (-{}, -{}%)\".format(\n", | 204 | 204 | "print(\"Shape Change: {} -> {} (-{}, -{}%)\".format(\n", | |
| " jawbone3_count, \n", | 205 | 205 | " jawbone3_count, \n", | |
| " jawbone4_count, \n", | 206 | 206 | " jawbone4_count, \n", | |
| " jawbone3_count - jawbone4_count, \n", | 207 | 207 | " jawbone3_count - jawbone4_count, \n", | |
| " round((jawbone3_count - jawbone4_count) / jawbone3_count * 100, 2)\n", | 208 | 208 | " round((jawbone3_count - jawbone4_count) / jawbone3_count * 100, 2)\n", | |
| " )\n", | 209 | 209 | " )\n", | |
| ")" | 210 | 210 | ")" | |
| ] | 211 | 211 | ] | |
| }, | 212 | 212 | }, | |
| { | 213 | 213 | { | |
| "cell_type": "markdown", | 214 | 214 | "cell_type": "markdown", | |
| "metadata": {}, | 215 | 215 | "metadata": {}, | |
| "source": [ | 216 | 216 | "source": [ | |
| "## Find consecutive minute walks" | 217 | 217 | "## Find consecutive minute walks" | |
| ] | 218 | 218 | ] | |
| }, | 219 | 219 | }, | |
| { | 220 | 220 | { | |
| "cell_type": "code", | 221 | 221 | "cell_type": "code", | |
| "execution_count": 37, | 222 | 222 | "execution_count": 37, | |
| "metadata": {}, | 223 | 223 | "metadata": {}, | |
| "outputs": [ | 224 | 224 | "outputs": [ | |
| { | 225 | 225 | { | |
| "name": "stdout", | 226 | 226 | "name": "stdout", | |
| "output_type": "stream", | 227 | 227 | "output_type": "stream", | |
| "text": [ | 228 | 228 | "text": [ | |
| "Iteration: 0, length: 377396\n", | 229 | 229 | "Iteration: 0, length: 377396\n", | |
| "Iteration: 1, length: 229752\n", | 230 | 230 | "Iteration: 1, length: 229752\n", | |
| "Iteration: 2, length: 170648\n", | 231 | 231 | "Iteration: 2, length: 170648\n", | |
| "Iteration: 3, length: 137484\n", | 232 | 232 | "Iteration: 3, length: 137484\n", | |
| "Iteration: 4, length: 178268\n", | 233 | 233 | "Iteration: 4, length: 178268\n", | |
| "Final, length: 94884\n" | 234 | 234 | "Final, length: 94884\n" | |
| ] | 235 | 235 | ] | |
| } | 236 | 236 | } | |
| ], | 237 | 237 | ], | |
| "source": [ | 238 | 238 | "source": [ | |
| "# prepare the data for the walk calculation\n", | 239 | 239 | "# prepare the data for the walk calculation\n", | |
| "current_vector = jawbone4[[\"user\", \"local_date\", \"local_minute_index\", \"steps\"]]\n", | 240 | 240 | "current_vector = jawbone4[[\"user\", \"local_date\", \"local_minute_index\", \"steps\"]]\n", | |
| "current_vector[\"add_count\"] = 1\n", | 241 | 241 | "current_vector[\"add_count\"] = 1\n", | |
| "current_vector = current_vector[current_vector[\"steps\"] > MINIMUM_STEPS_PER_MINUTE]\n", | 242 | 242 | "current_vector = current_vector[current_vector[\"steps\"] > MINIMUM_STEPS_PER_MINUTE]\n", | |
| "current_vector = current_vector[[\"user\", \"local_date\", \"local_minute_index\", \"add_count\"]]\n", | 243 | 243 | "current_vector = current_vector[[\"user\", \"local_date\", \"local_minute_index\", \"add_count\"]]\n", | |
| "\n", | 244 | 244 | "\n", | |
| "# define an iterative walk calculation (merging consecutive active minutes)\n", | 245 | 245 | "# define an iterative walk calculation (merging consecutive active minutes)\n", | |
| "def calculate_walk(cv):\n", | 246 | 246 | "def calculate_walk(cv):\n", | |
| " nv = cv.copy(deep=True)\n", | 247 | 247 | " nv = cv.copy(deep=True)\n", | |
| " nv[\"prev_minute_index\"] = nv[\"local_minute_index\"] - 1\n", | 248 | 248 | " nv[\"prev_minute_index\"] = nv[\"local_minute_index\"] - 1\n", | |
| "\n", | 249 | 249 | "\n", | |
| " # move midnight minutes to previous day\n", | 250 | 250 | " # move midnight minutes to previous day\n", | |
| " nv[nv[\"prev_minute_index\"] < 0][\"local_date\"] -= timedelta(days=1)\n", | 251 | 251 | " nv[nv[\"prev_minute_index\"] < 0][\"local_date\"] -= timedelta(days=1)\n", | |
| " nv[nv[\"prev_minute_index\"] < 0][\"prev_minute_index\"] = 1439\n", | 252 | 252 | " nv[nv[\"prev_minute_index\"] < 0][\"prev_minute_index\"] = 1439\n", | |
| " \n", | 253 | 253 | " \n", | |
| " nv = nv[[\"user\", \"local_date\", \"prev_minute_index\"]]\n", | 254 | 254 | " nv = nv[[\"user\", \"local_date\", \"prev_minute_index\"]]\n", | |
| " jv = cv.merge(nv, left_on=[\"user\", \"local_date\", \"local_minute_index\"], right_on=[\"user\", \"local_date\", \"prev_minute_index\"], how=\"inner\")\n", | 255 | 255 | " jv = cv.merge(nv, left_on=[\"user\", \"local_date\", \"local_minute_index\"], right_on=[\"user\", \"local_date\", \"prev_minute_index\"], how=\"inner\")\n", | |
| " jv[\"add_count\"] += 1\n", | 256 | 256 | " jv[\"add_count\"] += 1\n", | |
| " jv = jv[[\"user\", \"local_date\", \"local_minute_index\", \"add_count\"]]\n", | 257 | 257 | " jv = jv[[\"user\", \"local_date\", \"local_minute_index\", \"add_count\"]]\n", | |
| "\n", | 258 | 258 | "\n", | |
| " return jv \n", | 259 | 259 | " return jv \n", | |
| "\n", | 260 | 260 | "\n", | |
| "\n", | 261 | 261 | "\n", | |
| "# iteratively calculate the walk\n", | 262 | 262 | "# iteratively calculate the walk\n", | |
| "for i in range(0, MINIMUM_NUMBER_OF_MINUTES_FOR_A_WALK):\n", | 263 | 263 | "for i in range(0, MINIMUM_NUMBER_OF_MINUTES_FOR_A_WALK):\n", | |
| " print(\"Iteration: {}, length: {}\".format(i, current_vector.size))\n", | 264 | 264 | " print(\"Iteration: {}, length: {}\".format(i, current_vector.size))\n", | |
| " new_vector = calculate_walk(current_vector)\n", | 265 | 265 | " new_vector = calculate_walk(current_vector)\n", | |
| " current_vector = new_vector\n", | 266 | 266 | " current_vector = new_vector\n", | |
| "\n", | 267 | 267 | "\n", | |
| "print(\"Final, length: {}\".format(current_vector.size))\n", | 268 | 268 | "print(\"Final, length: {}\".format(current_vector.size))\n", | |
| "\n", | 269 | 269 | "\n", | |
| "consecutive_minutes = current_vector[[\"user\", \"local_date\", \"local_minute_index\"]].drop_duplicates()" | 270 | 270 | "consecutive_minutes = current_vector[[\"user\", \"local_date\", \"local_minute_index\"]].drop_duplicates()" | |
| ] | 271 | 271 | ] | |
| }, | 272 | 272 | }, | |
| { | 273 | 273 | { | |
| "cell_type": "markdown", | 274 | 274 | "cell_type": "markdown", | |
| "metadata": {}, | 275 | 275 | "metadata": {}, | |
| "source": [ | 276 | 276 | "source": [ | |
| "## Map consecutive minutes to 1hr and 3hr units" | 277 | 277 | "## Map consecutive minutes to 1hr and 3hr units" | |
| ] | 278 | 278 | ] | |
| }, | 279 | 279 | }, | |
| { | 280 | 280 | { | |
| "cell_type": "code", | 281 | 281 | "cell_type": "code", | |
| "execution_count": 110, | 282 | 282 | "execution_count": 111, | |
| "metadata": {}, | 283 | 283 | "metadata": {}, | |
| "outputs": [ | 284 | 284 | "outputs": [], | |
| { | 285 | |||
| "name": "stdout", | 286 | |||
| "output_type": "stream", | 287 | |||
| "text": [ | 288 | |||
| " index user local_date threehour walked\n", | 289 | |||
| "0 0 1 2015-07-22 2 2\n", | 290 | |||
| "1 3 1 2015-07-22 6 2\n", | 291 | |||
| "2 30 1 2015-07-23 2 2\n", | 292 | |||
| "3 50 1 2015-07-23 3 2\n", | 293 | |||
| "4 58 1 2015-07-23 5 2\n", | 294 | |||
| " user local_date threehour walked\n", | 295 | |||
| "0 1 2015-07-22 0 1.0\n", | 296 | |||
| "1 1 2015-07-22 1 1.0\n", | 297 | |||
| "2 1 2015-07-22 2 2.0\n", | 298 | |||
| "3 1 2015-07-22 3 1.0\n", | 299 | |||
| "4 1 2015-07-22 4 1.0\n", | 300 | |||
| "5 1 2015-07-22 5 1.0\n", | 301 | |||
| "6 1 2015-07-22 6 2.0\n", | 302 | |||
| "7 1 2015-07-22 7 1.0\n", | 303 | |||
| "8 1 2015-07-23 0 1.0\n", | 304 | |||
| "9 1 2015-07-23 1 1.0\n", | 305 | |||
| "10 1 2015-07-23 2 2.0\n", | 306 | |||
| "11 1 2015-07-23 3 2.0\n", | 307 | |||
| "12 1 2015-07-23 4 1.0\n", | 308 | |||
| "13 1 2015-07-23 5 2.0\n", | 309 | |||
| "14 1 2015-07-23 6 1.0\n", | 310 | |||
| "15 1 2015-07-23 7 1.0\n" | 311 | |||
| ] | 312 | |||
| } | 313 | |||
| ], | 314 | |||
| "source": [ | 315 | 285 | "source": [ | |
| "# calculate hour index and three hour index\n", | 316 | 286 | "# calculate hour index and three hour index\n", | |
| "consecutive_minutes[\"hour\"] = np.int_(np.floor(consecutive_minutes[\"local_minute_index\"] / 60))\n", | 317 | 287 | "consecutive_minutes[\"hour\"] = np.int_(np.floor(consecutive_minutes[\"local_minute_index\"] / 60))\n", | |
| "consecutive_minutes[\"threehour\"] = np.int_(np.floor(consecutive_minutes[\"hour\"] / 3))\n", | 318 | 288 | "consecutive_minutes[\"threehour\"] = np.int_(np.floor(consecutive_minutes[\"hour\"] / 3))\n", | |
| "\n", | 319 | 289 | "\n", | |
| "# calculate the number of walks per user, per hour\n", | 320 | 290 | "# calculate the number of walks per user, per hour\n", | |
| "walk_by_hours = consecutive_minutes[[\"user\", \"local_date\", \"hour\"]].drop_duplicates().reset_index()\n", | 321 | 291 | "walk_by_hours = consecutive_minutes[[\"user\", \"local_date\", \"hour\"]].drop_duplicates().reset_index()\n", | |
| "walk_by_hours[\"walked\"] = 2\n", | 322 | 292 | "walk_by_hours[\"walked\"] = 2\n", | |
| "\n", | 323 | 293 | "\n", | |
| "# calculate the number of walks per user, per three hour\n", | 324 | 294 | "# calculate the number of walks per user, per three hour\n", | |
| "walk_by_threehours = consecutive_minutes[[\"user\", \"local_date\", \"threehour\"]].drop_duplicates().reset_index()\n", | 325 | 295 | "walk_by_threehours = consecutive_minutes[[\"user\", \"local_date\", \"threehour\"]].drop_duplicates().reset_index()\n", | |
| "walk_by_threehours[\"walked\"] = 2\n", | 326 | 296 | "walk_by_threehours[\"walked\"] = 2\n", | |
| "\n", | 327 | 297 | "\n", | |
| "# generate hour vector and three hour vector\n", | 328 | 298 | "# generate hour vector and three hour vector\n", | |
| "hours = pd.DataFrame({\"hour\": range(0,24)})\n", | 329 | 299 | "hours = pd.DataFrame({\"hour\": range(0,24)})\n", | |
| "threehours = pd.DataFrame({\"threehour\": range(0, 8)})\n", | 330 | 300 | "threehours = pd.DataFrame({\"threehour\": range(0, 8)})\n", | |
| "\n", | 331 | 301 | "\n", | |
| "\n", | 332 | |||
| "walk_by_hours = walk_by_hours[:5]\n", | 333 | |||
| "walk_by_threehours = walk_by_threehours[:5]\n", | 334 | |||
| "\n", | 335 | |||
| "# generate complete product of vectors\n", | 336 | 302 | "# generate complete product of vectors\n", | |
| "def product_df(mat1, mat2):\n", | 337 | 303 | "def product_df(mat1, mat2):\n", | |
| " mat1 = mat1.drop_duplicates()\n", | 338 | 304 | " mat1 = mat1.drop_duplicates()\n", | |
| " mat2 = mat2.drop_duplicates()\n", | 339 | 305 | " mat2 = mat2.drop_duplicates()\n", | |
| "\n", | 340 | 306 | "\n", | |
| " temp = pd.DataFrame(list(product(mat1.values, mat2.values)))\n", | 341 | 307 | " temp = pd.DataFrame(list(product(mat1.values, mat2.values)))\n", | |
| " for i, acol in enumerate(mat1.columns):\n", | 342 | 308 | " for i, acol in enumerate(mat1.columns):\n", | |
| " temp[acol] = temp[0].apply(lambda x: x[i])\n", | 343 | 309 | " temp[acol] = temp[0].apply(lambda x: x[i])\n", | |
| " for i, acol in enumerate(mat2.columns):\n", | 344 | 310 | " for i, acol in enumerate(mat2.columns):\n", | |
| " temp[acol] = temp[1].apply(lambda x: x[i])\n", | 345 | 311 | " temp[acol] = temp[1].apply(lambda x: x[i])\n", | |
| " temp = temp.drop(columns=[0, 1])\n", | 346 | 312 | " temp = temp.drop(columns=[0, 1])\n", | |
| " return temp\n", | 347 | 313 | " return temp\n", | |
| "\n", | 348 | 314 | "\n", | |
| "measured_hour = product_df(walk_by_hours[[\"user\", \"local_date\"]], hours[[\"hour\"]])\n", | 349 | 315 | "measured_hour = product_df(walk_by_hours[[\"user\", \"local_date\"]], hours[[\"hour\"]])\n", | |
| "measured_threehour = product_df(walk_by_threehours[[\"user\", \"local_date\"]], threehours[[\"threehour\"]])\n", | 350 | 316 | "measured_threehour = product_df(walk_by_threehours[[\"user\", \"local_date\"]], threehours[[\"threehour\"]])\n", | |
| "\n", | 351 | 317 | "\n", | |
| "# pad the hourly walk data (fill in missing hours with 1s)\n", | 352 | 318 | "# pad the hourly walk data (fill in missing hours with 1s)\n", | |
| "padded_hours = walk_by_hours.merge(measured_hour, on=[\"user\", \"local_date\", \"hour\"], how=\"right\")\n", | 353 | 319 | "padded_hours = walk_by_hours.merge(measured_hour, on=[\"user\", \"local_date\", \"hour\"], how=\"right\")\n", | |
| "padded_hours = padded_hours[[\"user\", \"local_date\", \"hour\", \"walked\"]]\n", | 354 | 320 | "padded_hours = padded_hours[[\"user\", \"local_date\", \"hour\", \"walked\"]]\n", | |
| "padded_hours = padded_hours.fillna(1)\n", | 355 | 321 | "padded_hours = padded_hours.fillna(1)\n", | |
| "\n", | 356 | 322 | "\n", | |
| "# pad the walk data with 3 hours unit (fill in missing hours with 1s)\n", | 357 | 323 | "# pad the walk data with 3 hours unit (fill in missing hours with 1s)\n", | |
| "padded_threehours = walk_by_threehours.merge(measured_threehour, on=[\"user\", \"local_date\", \"threehour\"], how=\"right\")\n", | 358 | 324 | "padded_threehours = walk_by_threehours.merge(measured_threehour, on=[\"user\", \"local_date\", \"threehour\"], how=\"right\")\n", | |
| "padded_threehours = padded_threehours[[\"user\", \"local_date\", \"threehour\", \"walked\"]]\n", | 359 | 325 | "padded_threehours = padded_threehours[[\"user\", \"local_date\", \"threehour\", \"walked\"]]\n", | |
| "padded_threehours = padded_threehours.fillna(1)" | 360 | 326 | "padded_threehours = padded_threehours.fillna(1)" | |
| ] | 361 | 327 | ] | |
| }, | 362 | 328 | }, | |
| { | 363 | 329 | { | |
| 330 | "cell_type": "markdown", | |||
| 331 | "metadata": {}, | |||
| 332 | "source": [ | |||
| 333 | "## Pad unmeasured missing data with 0s\n", | |||
| 334 | "\n", | |||
| 335 | "For three hour window data, since it works as output vector, 0 padding is not done. Instead, missing output data is not used for training." | |||
| 336 | ] | |||
| 337 | }, | |||
| 338 | { | |||
| "cell_type": "code", | 364 | 339 | "cell_type": "code", | |
| "execution_count": null, | 365 | 340 | "execution_count": 141, | |
| "metadata": {}, | 366 | 341 | "metadata": {}, | |
| "outputs": [], | 367 | 342 | "outputs": [], | |
| "source": [ | 368 | 343 | "source": [ | |
| 344 | "# generate start and end date for each user\n", | |||
| 345 | "start_date = padded_hours.groupby([\"user\"])[\"local_date\"].min()\n", | |||
| 346 | "end_date = padded_hours.groupby([\"user\"])[\"local_date\"].max()\n", | |||
| "\n", | 369 | 347 | "\n", | |
| 348 | "# generate the user list\n", | |||
| 349 | "users = start_date.index\n", | |||
| 350 | "all_dates = pd.DataFrame({\"user\": [], \"local_date\": []})\n", | |||
| "\n", | 370 | 351 | "\n", | |
| "standard_minute_index = pd.Series(name=\"local_minute_index\", data=np.arange(0, 1440, 1))\n", | 371 | 352 | "def date_range(start_date, end_date):\n", | |
| 353 | " delta = end_date - start_date\n", | |||
| "\n", | 372 | 354 | "\n", | |
| "a_user = users[0]\n", | 373 | 355 | " for i in range(delta.days + 1):\n", | |
| "a_date = user_date2.local_date[0]\n", | 374 | 356 | " yield start_date + timedelta(days=i)\n", | |
| "\n", | 375 | 357 | "\n", | |
| "a_jawbone3 = jawbone3.loc[(jawbone3.user == a_user) & (jawbone3.local_date == a_date), :]\n", | 376 | 358 | "# generate the lists of dates between start and end date\n", | |
| 359 | "for userid in users:\n", | |||
| 360 | " current_user_dates = pd.DataFrame({\"user\": userid, \"local_date\": list(date_range(start_date[userid], end_date[userid]))})\n", | |||
| 361 | " \n", | |||
| 362 | " all_dates = pd.concat([all_dates, current_user_dates])\n", | |||
| "\n", | 377 | 363 | "\n", | |
| "vec = a_jawbone3[[\"local_minute_index\", \"steps\"]]\n", | 378 | 364 | "# generate the base vector for the padding\n", | |
| 365 | "all_dates_hour = product_df(all_dates[[\"user\", \"local_date\"]], hours[[\"hour\"]])\n", | |||
| "\n", | 379 | 366 | "\n", | |
| "steps = [0] * 1440\n", | 380 | 367 | "# final padded gait data\n", | |
| 368 | "padded_hours = padded_hours.merge(all_dates_hour, on=[\"user\", \"local_date\", \"hour\"], how=\"right\").fillna(0)\n", | |||
| "\n", | 381 | 369 | "\n", | |
| "for index, row in vec.iterrows():\n", | 382 | |||
| " steps[row.local_minute_index] += row.steps\n", | 383 | |||
| "\n", | 384 | 370 | "\n", | |
| "print(steps)\n", | 385 | 371 | "# save the data\n", | |
| "steps_series = pd.Series(name=\"steps\", data=steps)\n", | 386 | 372 | "padded_hours.to_csv(os.path.join(data_dir, \"padded_hours.csv\"), index=False)\n", | |
| "steps_series[\"over60\"] = (steps_series > 60) * 1\n", | 387 | 373 | "padded_threehours.to_csv(os.path.join(data_dir, \"padded_threehours.csv\"), index=False)" | |
| "\n", | 388 | |||
| "steps_series[\"roll\"] = steps_series.rolling(window=5, min_periods=1).sum()\n", | 389 | |||
| "\n", | 390 | |||
| "steps_series.roll.plot()\n", | 391 | |||
| "\n", | 392 | |||
| "\n" | 393 | |||
| ] | 394 | 374 | ] | |
| } | 395 | 375 | } | |
| ], | 396 | 376 | ], | |
| "metadata": { | 397 | 377 | "metadata": { | |
| "interpreter": { | 398 | 378 | "interpreter": { | |
| "hash": "80dbe1014b4652684caa329d41db00af3ae439be86b11eab7e35b518e5d8ab1a" | 399 | 379 | "hash": "80dbe1014b4652684caa329d41db00af3ae439be86b11eab7e35b518e5d8ab1a" | |
| }, | 400 | 380 | }, | |
| "kernelspec": { | 401 | 381 | "kernelspec": { | |
| "display_name": "Python 3.7.9 64-bit ('venv': venv)", | 402 | 382 | "display_name": "Python 3.7.9 64-bit ('venv': venv)", | |
| "language": "python", | 403 | 383 | "language": "python", | |
| "name": "python3" | 404 | 384 | "name": "python3" | |
| }, | 405 | 385 | }, | |
| "language_info": { | 406 | 386 | "language_info": { | |
| "codemirror_mode": { | 407 | 387 | "codemirror_mode": { | |
| "name": "ipython", | 408 | 388 | "name": "ipython", | |
| "version": 3 | 409 | 389 | "version": 3 | |
| }, | 410 | 390 | }, | |
| "file_extension": ".py", | 411 | 391 | "file_extension": ".py", | |
| "mimetype": "text/x-python", | 412 | 392 | "mimetype": "text/x-python", | |
| "name": "python", | 413 | 393 | "name": "python", | |
| "nbconvert_exporter": "python", | 414 | 394 | "nbconvert_exporter": "python", | |
| "pygments_lexer": "ipython3", | 415 | 395 | "pygments_lexer": "ipython3", | |
| "version": "3.7.9" | 416 | 396 | "version": "3.7.9" | |
| }, | 417 | 397 | }, | |
| "orig_nbformat": 4 | 418 | 398 | "orig_nbformat": 4 | |
| }, | 419 | 399 | }, | |
| "nbformat": 4, | 420 | 400 | "nbformat": 4, | |
| "nbformat_minor": 2 | 421 | 401 | "nbformat_minor": 2 | |
| } | 422 | 402 | } | |
| 423 | 403 | |||